Predicting Software Development Effort Using Artificial Neural Network (original) (raw)
Related papers
Neural Network Models for Software Development Effort Estimation: A Comparative Study
Software development effort estimation (SDEE) is one of the main tasks in software project management. It is crucial for a project manager to efficiently predict the effort or cost of a software project in a bidding process, since overestimation will lead to bidding loss and underestimation will cause the company to lose money. Several SDEE models exist; machine learning models, especially neural network models, are among the most prominent in the field. In this study, four different neural network models – Multilayer Perceptron, General Regression Neural Network, Radial Basis Function Neural Network, and Cascade Correlation Neural Network – are compared with each other based on: (1) predictive accuracy centered on the Mean Absolute Error criterion, (2) whether such a model tends to overestimate or underestimate, and (3) how each model classifies the importance of its inputs. Industrial datasets from the International Software Benchmarking Standards Group (ISBSG) are used to train and validate the four models. The main ISBSG dataset was filtered and then divided into five datasets based on the productivity value of each project. Results show that the four models tend to overestimate in 80% of the datasets, and the significance of the model inputs varies based on the selected model. Furthermore, the Cascade Correlation Neural Network outperforms the other three models in the majority of the datasets constructed on the Mean Absolute Residual criterion.
Procedia Computer Science, 2016
Software Effort Estimation models are hot topic of study over 3 decades. Several models have been developed in these decades. Providing accurate estimations of software is still very challenging. The major reason for such disappointments in projects are because of inaccurate software development norms; effort estimation is one such practice. Dynamically fluctuating environment of technology in software development industry make effort estimation further perplexing. One of the most commonly used algorithmic model for estimating effort in industry is COCOMO. Capability of machine learning particularly Artificial Neural Networks is to adjust a complex set of bond among the various independent and dependent variables. The paper proposes usage of ANN (Artificial Neural Network) based model technologically advanced using Multi Layered Feed Forward Neural Network which is given training with Back Propagation training method. COCOMO data-set is accustomed to test and train the network. Mean-Square-Error (MSE) and Mean Magnitude of Relative-Error (MMRE) are used as performance measurement indices. The experiment outputs suggest that the suggested model can provide better results and accurately forecast the software development effort.
A New High Performance Neural Network Model for Software Effort Estimation
2014
In this research, it is concerned with concerned with constructing software effort estimation models based on artificial neural network. The model is designed accordingly to improve the performance of the network that suits to the COCOMO model. Recent year the software industry is growing rapidly and people pay more attention on how to keep high efficiency in the process of software development and management. In the process of software development , time, cost, manpower are all critical factor. At the stage of software project planning, project manager will evaluate these parameter to get an efficient software develop process. Software effort evaluate is an important aspect which includes amount of cost, schedule, and manpower requirement. In this paper, it is proposed to use multilayer feed forward neural network to accommodate the model and its parameter to estimate software development effort. The network is trained with back propagation learning algorithm by iteratively process...
Empirical Software Engineering, 2012
An important factor for planning, budgeting and bidding a software project is prediction of the development effort required to complete it. This prediction can be obtained from models related to neural networks. The hypothesis of this research was the following: effort prediction accuracy of a general regression neural network (GRNN) model is statistically equal or better than that obtained by a statistical regression model, using data obtained from industrial environments. Each model was generated from a separate dataset obtained from the International Software Benchmarking Standards Group (ISBSG) software projects repository. Each of the two models was then validated using a new dataset from the same ISBSG repository. Results obtained from a variance analysis of accuracies of the models suggest that a GRNN could be an alternative for predicting development effort of software projects that have been developed in industrial environments.
A Efficient Neural Network Model for Software Effort Estimation
Software development effort estimation is the process of predicting the effort required to develop a software system. Estimating development effort accurately in the early stage of software life cycle plays a crucial role in effective project management. Effort estimation is a key factor for software project success, defined as delivering software of agreed quality and functionality within schedule and budget. Traditionally effort estimation has been used for planning and tracking project resources. It has become an important task. This paper proposed a neural network model for software effort estimation. This model has 3 layers. The train, validation and test data used are from COCOMO data set. Inputs and targets data randomly divided in train (60 %), validation (20%) and test (20%) group. When the number of neurons in hidden layer was 20, Number of training samples was 37, number of validation samples was 13 and number of testing samples was 13, the network has best performance. In this case, the value of training, validation and testing MSE was 0.01044, 0.0475 and 0.0375 respectively and value of training, validation and testing R was 0.9167, 0.7741 and 0.7410 respectively.
Schedule, effort and cost are three important elements of a successful project management. When it comes to predict them; making decisions based on only daily situation assessment reports is not enough anymore. Decision-making becomes more difficult in the case of uncertainty. However, administrators gain competitive advantage with the help of machine learning. In this study, it is aimed to predict software project effort using Artificial Neural Networks (ANNs). Unlike the other studies in the literature, authors preferred to evaluate the performance of ANNs from the perspective of one-class and binary classification, rather than estimate the exact project effort (person in months). For this purpose, the target attribute “effort” is categorized into two distinct groups using equal frequency discretization method. Analyzes are performed on a popular dataset named COCOMO 81 which is used by many researchers for effort estimation. Analysis are performed with R Programming Language and RStudio. Model performances are evaluated using 5-fold cross validation technique. In this study Multi-Layer Feed-Forward (MLFF) ANNs with Back Propagation Algorithm and Autoassociative Neural Networks (AANNs) is used as binary and one-class classification algorithms respectively. The optimum ANN architecture with the highest accuracy (0,72) and the lowest error (0,28) is obtained with MLFF ANNs.
Software Effort Estimation with Different Artificial Neural Network
2011
Failures of software are mainly due to the faulty project management practices, which includes effort estimation. Continuous changing scenarios of software development technology makes effort estimation more challenging. Ability of ANN(Artificial Neural Network) to model a complex set of relationship between the dependent variable (effort) and the independent variables (cost drivers) makes it as a potential tool for estimation. This paper presents a performance analysis of different ANNs in effort estimation. We have simulated four types of ANN created by MATLAB10 NNTool using NASA dataset.
Software development effort estimation (SDEE) is one of the main tasks in software project management. It is crucial for a project manager to efficiently predict the effort or cost of a software project in a bidding process, since overestimation will lead to bidding loss and underestimation will cause the company to lose money. Several SDEE models exist; machine learning models, especially neural network models, are among the most prominent in the field. In this study, four different neural network models—multilayer perceptron, general regression neural network, radial basis function neural network, and cascade correlation neural network—are compared with each other based on: (1) predictive accuracy centred on the mean absolute error criterion, (2) whether such a model tends to overestimate or underestimate, and (3) how each model classifies the importance of its inputs. Industrial datasets from the International Software Bench-marking Standards Group (ISBSG) are used to train and validate the four models. The main ISBSG dataset was filtered and then divided into five datasets based on the productivity value of each project. Results show that the four models tend to overestimate in 80 % of the datasets, and the significance of the model inputs varies based on the selected model. Furthermore, the cascade correlation neu-ral network outperforms the other three models in the majority of the datasets constructed on the mean absolute residual criterion. Keywords Software development effort estimation Á Neural network model Á Multilayer perceptron Á General regression neural network Á Radial basis function neural network Á Cascade correlation neural network
To Design and Implement Neural Network and Fuzzy Logic for Software Development Effort Prediction
International Journal of Computer Applications, 2013
One of the greatest challenges for software developers is forecasting the development effort for a software system for the last decades. The capability to provide a good estimation on software development efforts is necessitated by the project managers. Software effort estimation model divided into two main categories: algorithmic and non-algorithmic. These models too have difficulty in modeling the inherent complex relationships between the contributing factors, are unable to handle categorical data as well as lack of reasoning capabilities. The limitations of these models led to the exploration of the techniques which are soft computing based. In This paper we have compared neural network and fuzzy logic model for software development effort estimation. It will help us to make accurate software effort estimation by these estimation techniques
2012
Software effo rt estimation guides the bedding, planning, development and maintenance process of software product. Software development uses different paradigm like: procedure oriented, object oriented, Agile, Incremental, component based and web based etc. Different co mpanies use different techniques for their software project development. The available estimation techniques are not suitable for all types of software develop ment techniques. So there is a need of estimation technique that can be applied on all type of software. This paper we are evaluating the application of artificial neural networks in prediction of effort in conventional and Object Oriented Soft ware development approach. We have used feed-forward neural netwo rk created using MATLAB10 ( NN tool kit ) and applied on two different types of datasets, one for conventional software and another for object oriented software. The simulat ion results were studied and we found that artificial neural network model works very accurately on both types of software development techniques.